Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Degrees and education

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.84
    CloseOperation
    -0.77
     GoogleFonts
    -0.65
     vė
    -0.55
    Superclass
    -0.54
     convaincre
    -0.53
    AccessFile
    -0.53
    łoży
    -0.52
    łożyć
    -0.52
    šť
    -0.51
    POSITIVE LOGITS
     engineering
    0.52
     estekak
    0.47
     purpoſe
    0.46
    లాలు
    0.46
     poffe
    0.46
    Personensuche
    0.43
     juſ
    0.43
     fubject
    0.42
     conscience
    0.42
    anthene
    0.41
    Act Density 0.004%

    No Known Activations